Journal of Personalized Medicine

Background: Psychological health is an important aspect of health and well-being among adults with irritable bowel syndrome, yet the interrelationships among individual vulnerabilities, social experiences, perceived stress, and psychological health outcomes remain poorly understood. Objective: To characterize psychological health and examine direct and indirect associations of childhood adversity and adult attention-deficit/hyperactivity disorder-related symptoms within an adapted Stress Process Model. Design: Cross-sectional secondary analysis. Setting: The United States All of Us Research Program. Participants: 2,417 adults with electronic health record-documented irritable bowel syndrome and complete data on the primary analysis variables and covariates. Methods: Separate structural equation models examined childhood adversity and adult attention-deficit/hyperactivity disorder-related symptoms in relation to perceived stress, anxiety and depressive symptoms, and positive psychological well-being, with loneliness and perceived social support as psychosocial pathways. Models adjusted for sociodemographic and social-context factors. Results: The median age was 54.39 years; 80.7% were female and 84.4% were White. Moderate-to-high perceived stress was reported by 56.2%, at least moderate anxiety symptoms by 21.0%, and at least moderate depressive symptoms by 24.3%. Higher ACE-8 scores were associated with greater perceived stress, anxiety symptoms, and depressive symptoms and lower psychological well-being ({beta} = 0.063, 0.089, 0.116, and -0.100, respectively); corresponding associations for higher ASRS-6 scores were {beta} = 0.299, 0.355, 0.390, and -0.260. Loneliness-specific indirect associations were positive for perceived stress, anxiety, and depressive symptoms (ACE-8: {beta} = 0.023-0.034; ASRS-6: {beta} = 0.043-0.075) and negative for psychological well-being (ACE-8: {beta} = -0.039; ASRS-6: {beta} = -0.089; all p < .001). Social support-specific indirect associations were not significant in the ACE-8 model and were small and significant only for anxiety and depression in the ASRS-6 model ({beta} = 0.003-0.004). Conclusions: Psychological health among adults with irritable bowel syndrome was associated with interconnected individual and social factors within an adapted Stress Process Model. Childhood adversity and adult attention-deficit/hyperactivity disorder-related symptoms showed direct and indirect associations with psychological health, with loneliness emerging as the most consistent social factor. These findings support prospective investigation of individual vulnerabilities and social experiences in psychological health. The cross-sectional design does not establish temporal ordering or causal mediation.

Large language models (LLMs) are increasingly consulted for health advice, but they can produce fluent statements that are false or unsupported, known as hallucinations, and this risk is poorly characterised in low-resource languages such as Bangla. We measured hallucinations of locally deployable open-weight LLMs in Bangla diabetes question answering and tested whether retrieval-augmented generation (RAG) grounded in Bangladeshs National Guideline on Diabetes Mellitus reduces them. Forty patient questions spanning six clinical sub-domains were each answered twice, under zero-shot prompting, by Qwen3.5-9B, TigerLLM-9B, Qwen3.6-35B-A3B and Gemma-4-26B-A4B, and by BanglaDiaRAG, which adds hybrid dense (BGE-M3) and sparse (BM25) retrieval from a physician-reviewed Bangla guideline knowledge base to Qwen3.5-9B. Two physicians rated the 400 de-identified responses by consensus for medical accuracy, completeness, safety, readability and reliability on a 0-1 scale, and responses with accuracy below 0.70 were classified as hallucinated. Hallucination rates were 2.5% for Gemma-4-26B-A4B, 3.8% for TigerLLM-9B, 22.5% for Qwen3.6-35B-A3B and 77.5% for Qwen3.5-9B. Guideline grounding lowered the rate of Qwen3.5-9B to 11.3% (difference -66.3 percentage points; 95% CI -76.3 to -55.0) and raised every criterion by 0.24 to 0.38 points (Holm-adjusted p < 0.001). BanglaDiaRAG outscored Qwen3.6-35B-A3B on all five criteria and matched or exceeded TigerLLM-9B, but it remained below Gemma-4-26B-A4B in safety, readability and reliability, and its residual errors were specific, confident and potentially harmful. Guideline grounding can turn a weak general-purpose model into a much safer Bangla diabetes assistant, but the choice of base model mattered as much as retrieval and no configuration was free of hallucination, so clinical oversight remains essential before patient-facing use.

Importance: Conditions that are hard to diagnose, several more common in women, may be missing from electronic health records (EHRs), hiding patients from research cohorts and case finding. Objective: To measure how often the EHR contains a diagnosis code for chronic conditions that participants report, and to compare this with national survey benchmarks. Design, Setting, and Participants: This cross-sectional study used the All of Us Research Program Registered Tier Dataset v9. Participants were adults with EHR visits in both 12-month periods from July 2021 to June 2023 who completed a health history survey. We analyzed the data in October 2026. Exposures: Self-reported clinician diagnosis of 10 conditions with ongoing visits or treatment, as well as sex at birth, race and ethnicity, age, and years of EHR records. Main Outcomes and Measures: Share of participants reporting current care who had a qualifying diagnosis code, alone and relative to hypertension and type 2 diabetes, and the ratio of age-standardized coded shares to national survey prevalence. Results: Of 161,480 respondents, 114,610 (73,870 female [64.5%], median [IQR] age 63 [50-72] years) had at least 5 years of EHR records before the survey. Among those reporting current care, 84.6% (95% CI, 84.2%-85.0%) with hypertension and 87.0% (95% CI, 86.5%-87.6%) with type 2 diabetes had a code, compared with 41.3% (95% CI, 38.9%-43.8%) for endometriosis, 39.4% (95% CI, 34.3%-44.8%) for Lyme disease, and 24.4% (95% CI, 23.2%-25.6%) for chronic fatigue. Counting ICD-9-CM and other mapped codes, 55.3%, 51.5%, and 28.3%, respectively, had any qualifying record. Women had lower coded shares than men for hypertension, type 2 diabetes, obesity, depression, and anxiety (crude ratios 0.93-0.96, within-health-system ratios 0.98-1.02) and higher shares for migraine and fibromyalgia (within health systems, 1.11 [95% CI, 1.07-1.15] and 1.41 [95% CI, 1.29-1.57]). Age-standardized coded shares among active patients were 1.1 to 2.4 times national prevalence of the same self-reported diagnoses. Conclusions and Relevance: In this cross-sectional study, fewer than half of participants reporting ongoing care for chronic fatigue, Lyme disease, or endometriosis had a qualifying ICD-10-CM code. Linking each participant's report to their own record measured this gap directly.

Background: Epidermal Growth Factor Receptor (EGFR) tyrosine kinase inhibitors (TKIs) are widely used for EGFR-mutated non-small cell lung cancer (NSCLC) but have distinct toxicity profiles across generations. Aims: To investigate relationships between EGFR-TKI physicochemical, pharmacokinetic and pharmacological properties and drug-specific adverse drug reactions (ADRs) using national and global pharmacovigilance data. Methods: ADRs for erlotinib, afatinib and osimertinib were extracted from the UK MHRA Yellow Card scheme and WHO VigiAccess. Disproportionality analysis used reporting odds ratios (RORs). Signals were defined as ROR >2, lower 95% confidence interval >1 and >3 cases. Drug properties were curated from ChEMBL, emc, SmPC and EMA sources. Results: VigiAccess contained 88,662 individual case safety reports (163,619 ADRs) and Yellow Card contained 752 reports (1,814 ADRs). Four System Organ Class (SOC) signals were identified in VigiAccess and three in Yellow Card, with five additional Yellow Card Preferred Term signals. Eye disorders showed the strongest consistent association with erlotinib (VigiAccess ROR 4.33; Yellow Card ROR 4.18). Osimertinib was associated with pneumonitis (ROR 7.67) and pulmonary embolism (ROR 3.94). Afatinib showed psychiatric disorder signals in both databases (ROR 3.2-3.3) and diarrhoea (ROR 2.79). Neoplasm-related signals likely reflected confounding by indication. Conclusions: EGFR-TKIs demonstrate generation-specific pharmacovigilance profiles. Integration with drug properties supports mechanistic plausibility for several signals, while the atypical afatinib psychiatric association warrants further investigation. Findings are hypothesis-generating and require confirmation in controlled observational or mechanistic studies.

Introduction: Neuroinflammation is a known pathophysiologic mechanism in multiple sclerosis and a proposed mechanism in fibromyalgia and myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). Positron Emission Tomography (PET) imaging of the translocator protein (TSPO) has been widely used to measure neuroinflammation, though second-generation ligands are highly sensitive to a single nucleotide polymorphism, rs6971, resulting in high, mixed, and low affinity binders. It is unknown whether this polymorphism is associated with neuroinflammatory disorders. Materials and Methods: Eighty-six total participant genotypes for TSPO binding affinity were identified through Sanger sequencing (30 fibromyalgia, 21 ME/CFS, 11 multiple sclerosis, and 24 healthy controls). Associations between patient group and genotype were assessed with Fishers Exact test. Associations between genotype and symptom severity from self-report questionnaires were assessed with Kruskal-Wallis tests. Results: In the present study individuals with fibromyalgia, (ME/CFS), or multiple sclerosis were more likely to have a mixed- or low-affinity genotypes compared to healthy controls. Presence of the low or mixed genotypes were also associated with greater self-reported fatigue severity and depressive symptoms. Discussion: These findings should be confirmed in larger samples but suggest functional consequences of rs6971 polymorphism that may be related to the pathophysiology of pain and fatigue illnesses.

Background. Regulatory pressure to avoid confusingly similar drug names appears to have pushed manufacturers to coin more distinctive proprietary names, but no one has quantitatively analyzed this trend. Objective. To determine whether proprietary drug names became more orthographically distinctive (unusual in spelling) over time. Methods. We examined 1,321 US Food and Drug Administration (FDA) new molecular entity (NME) names (1985-2024), 2,769 FDA Orange Book trade names (1982-2026), 177,337 US pharmaceutical trademarks (1980-2026), and 1,273 generic names (1982-2025). Compared to prior names (including those already marketed) and ordinary English, we scored each name's character trigram (three-letter sequence) surprisal (statistical unexpectedness) and its edit-distance similarity to the closest existing names. Linear regression tested time trends, controlling for name length. Results. Mean NME trigram surprisal rose in every decade between the 1980s and 2020s, from 7.21 to 8.50 nats (natural-logarithm units, higher meaning less predictable), an 18% increase (b = 0.038, p < .001, R2 = 0.34). Half of 2020s names (7% in the 1980s) contained a letter sequence found in no common English word (e.g., Jesduvroq, Omvoh). Nearest-neighbor similarity fell after the early 1990s. Trademark data showed the same trend (b = 0.016, p < .001). Generic names showed a weaker trend (b = 0.011, R2 = 0.063). Conclusions. Over four decades, drug names became more orthographically distinctive, consistent with namespace crowding, deliberate efforts to avoid confusing names, and branding strategy. Because unfamiliar letter sequences can introduce other error pathways, increased distinctiveness does not necessarily imply improved safety.

Sickle cell disease (SCD) results from homozygosity or compound heterozygosity for a single point mutation in the beta hemoglobin gene. Despite carrying the same underlying causal mutation, patients exhibit highly heterogeneous clinical outcomes. Acute chest syndrome (ACS) is one of the leading causes of mortality in SCD. In this study, we aimed to identify genetic variants associated with ACS occurrence and recurrence (>5 episodes) in two SCD cohorts (OMG-SCD and Walk-PHaSST) of predominantly African ancestry and characterize their downstream molecular consequences. Although none of the SNPs reached the genome-wide threshold in the occurrence meta-analysis, we identified 40 independent genetic loci with p <10-5. However, the recurrence GWAS in OMG-SCD, which compared individuals with no prior history of ACS to individuals with a history of >5 episodes, identified one genome-wide significant locus along with 38 other independent loci with p <10-5. Survival analysis suggested lower survival probability among young ACS recurrence cases compared to controls or occurrence cases. Furthermore, molecular QTL analysis of ACS recurrence identified 42 SNP-protein and eight SNP-metabolite associations with p <10-3. Pathway and enrichment analysis identified secretory, platelet/hemostatic, and complement-mediated pathways, confirming the complex and heterogeneous pathophysiology of ACS. This study highlights the importance of a well-defined phenotype for identification of risk loci and elucidates the complex interplay of hemolytic, inflammatory, and cellular organization pathways that warrants further evaluation through large-scale multi-omic studies of SCD patients. Ultimately, the more extreme phenotype of ACS recurrence may be a more informative phenotype for analysis, risk prediction, and therapeutic targeting.

Purpose: Posterior pharyngeal wall (PPW) thickening is a common structural manifestation of treatment-related internal lymphedema in patients with head and neck cancer and can be evaluated using lateral videofluoroscopic images acquired during modified barium swallow (MBS) studies. However, no standardized method currently exists for quantitative measurement. Methods: This two-phase methodological study first conducted a scoping review to characterize existing approaches to PPW thickness measurement and identify the principal factors contributing to variation in PPW thickness measurement. Eight studies were identified with variation observed across these measurement factors. An empirical reliability study was then performed using 107 MBS studies from 93 Head and Neck Cancer patients. Two independent raters annotated 10 anatomical landmarks on pre-swallow and post-swallow resting frames, and a computer-assisted algorithm quantitatively generated seven candidate PPW thickness measurements based on different vertebral reference points and measurement directions. Reliability was assessed intraclass correlation coefficients (ICCs). Results: Inter-rater reliability was highest for the measurement originating from the midpoint of C3 and extending perpendicular to the anterior C3 surface (ICC, 0.78; 95% CI, 0.72-0.83). Among the normalization references, C2-C4 vertebral length demonstrated greater reliability than C3 vertebral length, with an ICC of 0.88 (95% CI, 0.85-0.91). No significant differences were observed between pre-swallow and post-swallow PPW thickness measurements across the evaluated approaches. Conclusions: These findings provide a methodological foundation for more standardized and reliable quantification of PPW thickness, with potential to expand the role of MBS from the functional evaluation of swallowing to include quantitative characterization of pharyngeal structural abnormalities.

Purpose Prescribing to lactating women is constrained by limited evidence. Published compatibility classifications provide clinical guidance and a discrete research comparator. How often prescribing diverges from that guidance, and what characteristics are associated with divergence, is unknown at national scale. Methods Retrospective analysis of prescriptions filled during lactation, identified in the 2012-2014 MarketScan Commercial Claims Database. Prescriptions were classified as concordant (Hale's lactation risk category L1-L3) or discordant (L4-L5). Multivariable logistic regression identified factors associated with concordance. Results Of 96,484 new prescriptions, 95,710 (99.2%) were concordant and 774 (0.8%) were discordant. Discordant prescriptions were filled later after delivery (median 59 vs 33 days) and had a day supply three times longer (30 vs 10 days). In multivariable analysis (N=28,732), concordant prescriptions were associated with maternal age under 35 (adjusted odds ratio (aOR)=1.34, 95% confidence interval (CI): 1.02-1.75) and chronic-condition medications (aOR=10.94, 95% CI: 6.47-18.50), and were less likely within 14 days of delivery (aOR=0.53, 95% CI: 0.38-0.73) and with each additional day of supply (aOR=0.96, 95% CI: 0.96-0.96). Compared with family practice, concordance did not differ for obstetric, internal medicine, or emergency medicine prescriptions, but prescriptions from other provider types had lower odds of concordance (aOR=0.57, 95% CI: 0.41-0.79). Conclusions Prescribing during lactation was overwhelmingly concordant with published compatibility guidance; the rare divergence was patterned by prescription and prescriber characteristics. Because the categories are an expert classification rather than consensus guidance, divergence should not be read as inappropriate prescribing.

Importance. Plasma phosphorylated tau 217 (p-tau217) is entering clinical use with fixed diagnostic threshold that do not account for kidney function. Chronic kidney disease (defined as estimated glomerular filtration rate (eGFR) below 60 mL/min/1.73 m2), raises plasma p-tau217 concentrations and can produce false positive results. It remains unclear whether milder reductions in kidney function, above the CKD threshold, have the same effect. Objective. To determine whether plasma p-tau217 is elevated with mildly reduced kidney function, above the chronic kidney disease threshold, in adults without neurological disease. Design. Cross-sectional analysis of a cohort enrolled between 2023 and 2025 and biomarker analysis blinded to clinical data. Setting. Two private psychiatric inpatient facilities in Australia. Participants. Adults admitted with psychiatric disorders and free of neurological disease. Exposures. eGFR calculated from serum creatinine using the CKD-EPI 2021 equation. Main Outcomes and Measures. Plasma p-tau217, neurofilament light chain (NfL), and glial fibrillary acidic protein (GFAP), measured on the Simoa platform. Multivariable linear regression compared eGFR groups (< 60, 60 to 90, and [&ge;] 90 mL/min/1.73 m2), adjusted for age, BMI, and sex. Results. Among 180 participants (median age, 50.5 years [IQR, 38.0-61.5]; 94 [52%] female), eGFR was [&ge;] 90 mL/min/1.73 m2 in 106 (59%), 60 to 90 in 61 (34%), and < 60 in 13 (7.2%). Compared with an eGFR [&ge;] 90, plasma p-tau217 was 36% higher in both the 60 to < 90 group ({beta} = 0.42 [95% CI: 0.11, 0.74]; P = .008) and 116% higher in the < 60 group ({beta} = 1.05 [95% CI: 0.43, 1.72]; P = .002). Plasma NfL and GFAP were elevated in the < 60 group but differences in the 60 to < 90 group did not reach significance. Modelled continuously, plasma p-tau217 was 9.5% lower per 10 mL/min/1.73 m2 higher eGFR (95% CI: 3.3%, 15.4%). Conclusions and Relevance. Plasma p-tau217 was elevated in adults with mildly reduced kidney function, above the CKD threshold, in a cohort free of neurological disease. Kidney function across its full range should be incorporated into plasma p-tau217 reference ranges and clinical interpretation to reduce false positive and false negative results.

Background: Chronic kidney disease (CKD) may progress to stage 5 CKD (end-stage renal disease, ESRD), but stage-associated molecular alterations remain incompletely characterized. This study aimed to identify candidate biomarkers associated with CKD and ESRD. Methods: Two discovery datasets comparing CKD or ESRD with healthy controls were analyzed using differential expression analysis and weighted gene co-expression network analysis. Candidate genes were identified by intersecting differentially expressed genes with key co-expression modules, followed by protein-protein interaction network analysis using Degree, Closeness, and Maximal Clique Centrality algorithms. Candidate genes were evaluated in independent GEO validation datasets and further examined by quantitative real-time PCR and western blotting using clinical blood samples. Results: Ten hub genes were identified, among which EPB42, KLF1, and H3F3A were prioritized for further evaluation. EPB42 showed decreased expression in CKD but increased expression in ESRD, indicating an opposite-direction pattern between the two disease states. KLF1 showed no significant difference between healthy controls and CKD but was increased in ESRD, whereas H3F3A was increased in CKD and further increased in ESRD. Functional enrichment analysis highlighted processes related to oxygen transport, mitochondrial function, muscle-associated processes, and inflammation, suggesting possible involvement of hypoxia-associated oxidative injury and ferroptosis-related processes. Conclusions: Integrated transcriptomic and experimental analyses identified EPB42, KLF1, and H3F3A as candidate stage-associated biomarkers in CKD and ESRD. In particular, the opposite-direction expression pattern of EPB42 may provide additional molecular information for distinguishing CKD from ESRD.

Objective: To determine how cohort versus nested case-control (NCC) design affects EHR-based prediction of a rare outcome. Materials and Methods: We compared two cohort and five NCC designs for predicting early-onset gastrointestinal cancer using L1-regularized logistic regression (LASSO), XGBoost, and multilayer perceptron (MLP). Models underwent nested five-fold cross-validation with model-specific hyperparameter tuning and temporal evaluation in a held-out prospective cohort representing intended deployment. Model discrimination was assessed using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). Model calibration was assessed using Brier scores and calibration plots before and after recalibration with isotonic regression. Feature-ranking similarity was quantified using rank-biased overlap. Results: The cohort development datasets included 256,854-415,529 patients, with 2-yr cumulative incidence of 0.12%-0.17%, compared with approximately 9% in the 1:10 matched NCC datasets. NCC designs generally produced higher internal discrimination, but temporal performance varied by algorithm and index-date definition. Cohort designs achieved the highest temporal AUPRC for LASSO (0.068), whereas diagnosis-anchored NCC achieved the highest temporal AUPRC for XGBoost (0.086) and MLP (0.070). Temporal AUPRC generally decreased as the required lead time before diagnosis increased. Raw predicted probabilities substantially overestimated observed risks in the temporal cohort. Isotonic recalibration improved probability scaling while largely preserving discrimination, although residual miscalibration remained. Cohort-based feature rankings were more consistent across algorithms, whereas NCC-based rankings depended more strongly on algorithm and index-date anchoring. Conclusion: Study design should be selected and evaluated according to the intended clinical prediction task and deployment setting.

Personalized medicine aims to tailor treatments to individual patients, but its implementation is limited by scarce clinical resources and heterogeneous treatment effects. Electronic health records now offer longitudinal data that can support data-driven therapy selection. We focus on SGLT2 inhibitors, medications with broad metabolic and cardiovascular benefits, whose clinical impact varies significantly based on individual patient profiles. We propose a counterfactual Structural Causal Model (SCM) to estimate individual treatment effects (ITE) of SGLT2 inhibitors from observational data. The model assumes counterfactual stability and uses a Gumbel-Max sampling mechanism to capture stochastic treatment assignment while enabling differentiable inference. Optimal treatments are defined by maximizing the counterfactual value of future diagnostic outcomes. We evaluate the Counterfactual Gumbel-Max SCM using a doubly robust value estimator and show that, across diagnostic categories, it outperforms real-world prescriptions in predicted treatment value, highlighting subpopulations where SGLT2 inhibitors yield superior outcomes. By integrating causal inference with electronic health data, this framework provides individualized counterfactual reasoning about SGLT2 treatment effects and can support clinicians in identifying optimal therapies for type 2 diabetes and comorbid conditions.

Objectives To evaluate discrepancies between radiologists and referring physicians in the interpretation of diagnostic probabilities conveyed by common Japanese expressions used in radiology reports. Materials and Methods Fifteen expressions commonly used to convey diagnostic probabilities in radiology reports were selected by five attending radiologists. An anonymous online survey was distributed to 26 radiologists and 33 referring physicians at a single institution. Participants assigned a diagnostic probability (from 0% to 100% in 10% increments) to each expression. Differences in median probabilities between radiologists and referring physicians were analyzed using the Mann-Whitney U test. Variability in interpretation was assessed using interquartile range (IQR), with IQR [&ge;] 30% defined as substantial variability. Results All radiologists (26/26) and 97% of referring physicians (32/33) completed the survey. Seven of the 15 expressions showed statistically significant differences in interpretation between radiologists and referring physicians: "c/w" (80% vs. 60%; p = 0.031), the Japanese equivalents of "present" (100% vs. 100%; p = 0.024), "suspect of" (80% vs. 70%; p = 0.007), "possibly" (50% vs. 70%; p < 0.001), "unlikely" (10% vs. 10%; p = 0.022), "cannot be ruled out" (25% vs. 40%; p < 0.001), and "not inconsistent with" (80% vs. 90%; p = 0.008). Substantial variability in interpretation (IQR [&ge;] 30%) was observed for four expressions: "cannot be ruled out" (IQR, 10%-40%), "s/o" (IQR, 60%-90%), "c/w" (IQR, 50%-90%), and "not inconsistent with" (IQR, 70%-100%). Conclusion This study revealed that nearly half of the Japanese expressions commonly used to convey diagnostic probabilities were interpreted differently by radiologists and referring physicians. These discrepancies highlight the need for a standardized lexicon to improve clarity and consistency in radiology reporting.

Objective A diversity of approaches and cohorts have been published in research literature for suicide risk estimation, leading to some uncertainty around which factors and conditions are most strongly contributing to risk. Methods exist for weighting estimates by propensity score, removing simplifying the interpretation of model effects. Few studies have explored the use of these tools to assess when the effect of certain factors is uncertain or inconsistent. Method A mix of 1,001,737 suicide decedents and living patients were evaluated for suicide risk, relying on a subset of commonly identified factors: demographics, psychiatric conditions, substance use disorders, and social needs. Care utilization patterns were then assessed controlling for these factors in a hospital care setting. Four methods were considered for controlling multivariate confounding of odds predicting death by suicide: multivariate logistic regression, 1-to-1 sample matching, inverse propensity weighting (IPTW), and entropy balancing (EBAL). Results Test statistics showed suicide decedents were much more likely to have various psychiatric and substance use diagnoses, social needs and more likely to heightened care utilization across sampling intervals. Greater utilization was found close to date of death. Effect sizes after IPTW and EBAL weighting were also generally greater than would have been documented by regression alone. Conclusions Propensity weighting is a useful alternative to exploring nuanced effects, especially when the direction and strength of an association differ from traditional statistics. By weighting, the overall imbalance of cases remains consistent and effect terms might reflect more nuanced associations than regression or sample matching alone.

Background: Conventional performance metrics do not indicate whether artificial intelligence (AI)-platforms and radiologists are right or wrong on the same examinations, nor whether their non-agreement is more often beneficial or harmful. Objective: To develop, illustrate, and apply directional metrics quantifying non-agreement between radiologists and AI-platforms against a common reference standard, and to adapt a fragility-based framework for quantifying the statistical robustness of these metrics. Methods: We defined Positive Non-Agreement (PNA, AI-platform correct, radiologist incorrect), Negative Non-Agreement (NNA, radiologist correct, AI-platform incorrect), and Net Non-Agreement (NENA, their difference). Metrics were illustrated in three hypothetical scenarios of 1,000 examinations each and applied to three previously published AI-radiologist studies on pulmonary embolism and mammography. Bootstrap confidence intervals were calculated, and a reclassification fragility index (FI) quantified the minimum case reclassification needed to remove statistical support for NENA's direction. Results: In illustration, NENA was positive in two scenarios and negative in one. In the three published studies, NENA ranged from -4.18% to +10.74% and decreased consistently with increasing radiologist experience (junior residents, +6.27%; consultants, +1.45%), a gradient driven primarily by declining PNA with modest increase in NNA. The reclassification FI was defined for all three illustrative scenarios (range, 0.10%-1.70%) and for six of the seven comparisons from these studies (range, 0.34%-4.31%), but not for the weakest comparison, whose confidence interval for NENA included zero. Conclusions: PNA, NNA, and NENA provide a directional, case-level complement to conventional performance metrics for AI-radiologist non-agreement. The accompanying reclassification FI offers a statistically grounded, generalizable method for quantifying their robustness.

Biomedical artificial intelligence (AI) increasingly relies on heterogeneous data sources, yet differences in data structure, terminology, evidence quality, and provenance complicate their integration into reliable knowledge resources. Here, we develop an evidence-aware framework for processing and integrating heterogeneous pharmacovigilance data from FDA Adverse Event Reporting System (FAERS) reports, biomedical literature, clinical trials, and electronic health records in Mass General Brigham. The framework combines large language model (LLM)-based information extraction, ontology-driven semantic normalization, cross-source evidence assessment, statistical and machine learning-based prioritization, and ingredient-based adverse drug event (ADE) relationship inference to transform heterogeneous evidence into a structured and evidence-based knowledge resource. The constructed knowledge system contains 11,588 drug nodes, 44,843 ingredient nodes, 3,275 ADE nodes, 993 indication nodes, and more than 2.47 million relationships, with each drug-ADE relationship assigned a confidence score. We further developed a drug-level web interface for accessing the knowledge resource and validated its utility in downstream AI tasks. Specifically, incorporating the developed knowledge resource improved the comprehensiveness, relevance, and overall quality of LLM-based drug-specific ADE synthesis and improved the precision and F1 score of clinical ADE relation extraction. These results demonstrate that AI-assisted processing combined with evidence-aware curation can transform heterogeneous biomedical evidence into reusable, AI-ready knowledge with explicit provenance and evidence strength information. The framework provides a general strategy for integrating heterogeneous biomedical data to support reproducible knowledge construction and downstream biomedical AI applications.

Computed tomography (CT) interpretation requires recognition of the anatomical level of each slice. Classification may facilitate preprocessing and AI-assisted fracture diagnosis. We developed deep learning models to classify craniofacial CT slices into six anatomical categories. A total of 11,769 images were collected from a multicenter database involving 10 Japanese university hospitals and the public Head-Neck-Radiomics-HN1 dataset. Patients were divided into training (70%) and evaluation (30%) sets. Five CNN architectures were trained from scratch, and hard- and soft-voting ensembles were evaluated. Individual-model accuracy ranged from 94.72% to 96.09%; the hard-voting ensemble achieved 96.46% accuracy (Cohen's k = 0.954). Although performance differed among individual models (Cochran's Q = 99.29, p < 0.001), the ensemble did not significantly outperform EfficientNetV2B1 (McNemar's p = 0.163). Errors occurred mainly between adjacent anatomical regions. Deep learning can classify craniofacial CT slices accurately and may support automated dataset organization and AI-assisted fracture diagnosis. External validation is needed.

Background: Ambient artificial-intelligence (AI) scribes are being deployed beyond medicine into allied-health practice, but comparative evidence mainly concerns physician documentation. Objective: To compare quality and transcript-grounded clinical-risk error burden of AI-generated and allied health professional notes from identical simulated consultations. Methods: Paired simulation across dietetics, physiotherapy, occupational therapy and speech and language therapy (five consultations each; 20 pairs; 40 notes). Heidi generated an unedited first-draft note and a professional documented each encounter. Professionals rated PDQI-9 quality. Professional and automated review identified unsupported statements and omissions; two language models graded clinical risk. Co-primary outcomes were PDQI-9 score and Critical+High error density. Results: Mean PDQI-9 scores were 38.45 and 35.05 for AI and professional notes (paired difference +3.40, 95% CI +0.01 to +6.79; Wilcoxon p=0.042; dz=0.47). The Bayesian estimate was +3.47 (94% equal-tailed credible interval +0.66 to +6.30; P[AI>professional]=0.989). Automated-reviewer all-error density was 3.35 vs 8.55 per note (professional-minus-AI difference 5.20, 95% CI 3.85 to 6.55); omission density was 1.45 vs 5.20 (difference 3.75, 2.80 to 4.65). Critical+High density was 0.35 vs 0.75 (difference 0.40, -0.10 to 1.00). The pooled quality result was driven principally by dietetics. Conclusions: AI-generated notes achieved modestly higher pooled quality and fewer transcript-grounded errors, chiefly omissions; serious-error evidence was inconclusive. Small discipline samples and incomplete ground truth preclude safety or discipline-wide superiority claims.

Polyendocrine metabolic ovarian syndrome (PMOS) and early-life irregular cycles (ELIC) carry higher metabolic risks, but real-world glycemic patterns remain inadequately characterized. We analyzed 247,316 continuous glucose monitoring (CGM) days from 716 consented and enrolled participants (11/2019-08/2026) in the Apple Women's Health Study, using cluster-weighted generalized estimating equations to evaluate associations between PMOS, ELIC, and glycemic metrics. Same-day wearable-assessed physical activity, digital dietary logs, and medication health records were assessed as effect modifiers. Compared to participants without PMOS and with regular cycles, those with PMOS had higher mean glucose (6.81 mg/dL; 95% CI: -0.70, 14.72) and %observations above target range (3.77%; 95% CI: 0.04, 8.14). Estimates were smaller-in-magnitude for participants without PMOS but with ELIC, and larger for PMOS with androgen excess. Meeting activity goals, consuming protein-/fiber-rich diets, or using metformin/GLP-1 receptor agonists attenuated these associations. PMOS/ELIC were associated with unfavorable glycemic profiles, suggesting opportunities for risk identification and modification.